An estimate of a functional capacity such as VO2Max is made by applying the vital signs of a monitored human to a trained encoding neural network producing a cardio profile vector. The vector is applied to a trained functional capacity (VO2Max) neural network to estimate the functional capacity. Once estimated, an action is taken.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A method for treating and improving the cardiopulmonary health of humans, the method comprising: configuring an encoding neural network to accept as input a time series of a selected plurality of cardiopulmonary variables, and to generate a multi-element cardio profile vector; configuring a function generator neural network to generate weights when supplied with the cardio profile vector as input; configuring an estimation neural network to accept as input a time series of a subset of the selected plurality of cardiopulmonary variables, the subset omitting at least one excluded variable, and to generate an estimate of the at least one excluded variable, wherein the estimation neural network is configured using the weights output by the function generator network as weights of connections between nodes in the estimation neural network; iteratively training in tandem and by a plurality of iterations the encoding neural network to produce a trained encoding neural network and the function generator neural network to produce a trained function generator neural network, the training using an error metric inclusive of the difference between the at least one excluded variable and the estimate of the at least one excluded variable generated by the estimation neural network, wherein for each of the iterations and for each of a plurality of training human subjects, a first duration of training data comprising a substantially contiguous time series of the selected plurality of cardiopulmonary variables from a training human subject is input to the encoding neural network, a second duration of the training data, substantially nonoverlapping in time with the first duration, comprising a substantially contiguous time series of the selected plurality of cardiopulmonary variables from the training human subject, provides input to the estimation neural network and wherein the estimation neural network provides the estimate of the at least one excluded variable; configuring a functional capacity estimator to accept as input a cardio profile vector generated by the trained encoding neural network, and to output an estimate of a metric of functional capacity, training the functional capacity estimator using a plurality of matched examples to produce a trained functional capacity estimator, each of the matched examples comprising a cardio profile vector matched with a corresponding measured functional capacity metric of that person, to enable regression of an input of a cardio profile vector to an estimate of the metric of functional capacity; deploying the trained encoding neural network and the trained functional capacity estimator, to accept as input a duration of monitored data from a monitored human subject, comprising substantially contiguous time series of the selected plurality of cardiopulmonary variables, generating a current cardio profile vector for the monitored human subject, and generating from application of the current cardio profile vector to the trained functional capacity estimator a current estimate of the metric of functional capacity; and based upon the current estimate of functional capacity, performing one or more actions selected from the group consisting of: displaying the current estimate in a time series with prior estimates to a clinician for review of possible health changes in the monitored human subject; comparing the current estimate to prior estimates and testing for a change whereupon an alert is triggered to a clinician to investigate the health of the monitored human; comparing the current estimate to prior estimates and testing for a change whereupon a questionnaire is sent to the monitored human subject; comparing the current estimate to prior estimates and testing for a change whereupon an entry is made in the medical record of the monitored human subject indicating a change in health of the monitored human subject occurred; comparing the current estimate to estimates from other monitored human subjects, in order to quantify health affects between at least a control group receiving a first intervention and a test group receiving a second intervention in a clinical trial; and controlling the operation or setting a parameter of a medical device associated with treating or monitoring the monitored human subject.
2. The method of claim 1 , wherein the functional capacity is VO2Max.
3. The method of claim 1 , wherein the time series of selected plurality of cardiopulmonary variables is obtained by sensors that are non-invasively secured to the skin of the humans.
4. The method of claim 1 , wherein the time series of selected plurality of cardiopulmonary variables is obtained by sensors and the sensors are selected from the group consisting of a camera, an electrocardiographic sensor, a light sensor, an accelerometer, an RF energy sensor, a temperature sensor, and a gyroscopic sensor.
5. The method of claim 1 , wherein the functional capacity estimator generates the current estimate of the metric of functional capacity using one of: a linear regression technique, a decision tree, a random forest estimation, or a gradient boosting model.
6. The method of claim 1 , wherein functional capacity estimator comprises an estimation neural network.
7. The method of claim 1 , wherein the cardiopulmonary variables comprise one or more of: a heart rate, a measure of physical activity or motion, a time domain heart rate variability, a respiration rate, a tilt angle, an A-fib probability, and a sample time difference.
8. The method of claim 1 , wherein the current cardio profile vector comprises a plurality of real numbers, each of the real numbers associate with one or more of the cardiopulmonary variables.
9. A system that is configured to treat and improve the cardiopulmonary health of humans, the system comprising: a sensor for obtaining a duration of monitored data from a monitored human subject, comprising substantially contiguous time series of a selected plurality of cardiopulmonary variables, the sensor being deployed with a monitored human subject; a control circuit, the control circuit coupled to the sensor, the control circuit is configured to: receive the duration of monitored data; apply the duration of monitored data to a trained encoding neural network and responsively create a current cardio profile vector for the monitored human subject; generate from the current cardio profile vector a current estimate of the metric of functional capacity by applying the current cardio profile vector to a trained functional capacity estimation neural network; wherein the trained functional capacity estimation neural network was created using a plurality of matched examples to produce the trained functional capacity estimation neural network, each of the matched examples comprising a cardio profile vector matched with a corresponding measured functional capacity metric of that person, to enable regression of an input of a cardio profile vector to an estimate of the metric of functional capacity; and wherein, based upon the current estimate of functional capacity, one or more actions are performed, the one or more actions selected from the group consisting of: the control circuit renders a display on a display screen of the current estimate in a time series with prior estimates to a clinician for review of possible health changes in the monitored human subject; the control circuit compares the current estimate to prior estimates and testing for a change whereupon an electronic alert is triggered and transmitted to a clinician to investigate the health of the monitored human; the control circuit compares the current estimate to prior estimates and testing for a change whereupon the control circuit transmits an electronic questionnaire to the monitored human subject; the control circuit compares the current estimate to prior estimates and testing for a change whereupon the control circuit makes an entry in an electronic medical record of the monitored human subject indicating a change in health of the monitored human subject occurred; the control circuit compares the current estimate to estimates from other monitored human subjects, in order to quantify health affects between at least a control group receiving a first intervention and a test group receiving a second intervention in a clinical trial; and the control circuit transmits an electronic control signal that controls the operation or sets a parameter of a medical device associated with treating or monitoring the monitored human subject.
10. The system of claim 9 , wherein an encoding neural network is configured to accept as input a time series of a selected plurality of cardiopulmonary variables, and to generate a multi-element cardio profile vector; wherein a function generator neural network is configured to generate weights when supplied with the cardio profile vector as input; wherein an estimation neural network is configured to accept as input a time series of a subset of the selected plurality of cardiopulmonary variables, the subset omitting at least one excluded variable, and to generate an estimate of the at least one excluded variable, wherein the estimation neural network is configured using the weights output by the function generator network as weights of connections between nodes in the estimation neural network; wherein the encoding neural network and the function generator neural network are trained in tandem and by a plurality of iterations, the training the encoding neural network producing the trained encoding neural network and the training of the function generator neural network producing a trained function generator neural network, the training of the encoding neural network and the function generator neural network using an error metric inclusive of the difference between at least one excluded variable and the estimate of the at least one excluded variable generated by the estimation neural network, wherein for each of the iterations: a first duration of training data comprising a substantially contiguous time series of the selected plurality of cardiopulmonary variables from a training human subject is input to the encoding neural network, a second duration of the training data, substantially nonoverlapping in time with the first duration, comprising a substantially contiguous time series of the selected plurality of cardiopulmonary variables from the training human subject, provides input to the estimation neural network and wherein the estimation neural network provides the estimate of the at least one excluded variable.
11. The system of claim 9 , wherein the functional capacity is VO2Max.
12. The system of claim 9 , wherein the sensors are selected from the group consisting of a camera, an electrocardiographic sensor, a light sensor, an accelerometer, an RF energy sensor, a temperature sensor, and a gyroscopic sensor.
13. The system of claim 9 , wherein the cardiopulmonary variables comprise one or more of: a heart rate, a measure of physical activity or motion, a time domain heart rate variability, a respiration rate, a tilt angle, an A-fib probability, and a sample time difference.
14. The system of claim 9 , wherein the current cardio profile vector comprises a plurality of real numbers, each of the real numbers associate with one or more of the cardiopulmonary variables.
15. A system that is configured to treat and improve the cardiopulmonary health of humans, the system comprising: an encoding neural network, the encoding neural network configured to accept as input a time series of a selected plurality of cardiopulmonary variables, and to generate a multi-element cardio profile vector; a function generator neural network, the function generator neural network configured to generate weights when supplied with the cardio profile vector as input; an estimation neural network, the estimation neural network configured to accept as input a time series of a subset of the selected plurality of cardiopulmonary variables, the subset omitting at least one excluded variable, and to generate an estimate of the at least one excluded variable, wherein the estimation neural network is configured using the weights output by the function generator network as weights of connections between nodes in the estimation neural network; a control circuit, the control circuit configured to iteratively train in tandem and by a plurality of iterations (1) the encoding neural network to produce a trained encoding neural network and (2) the function generator neural network to produce a trained function generator neural network, the training using an error metric inclusive of the difference between the at least one excluded variable and the estimate of the at least one excluded variable generated by the estimation neural network, wherein for each of the iterations, a first duration of training data comprising a substantially contiguous time series of said selected plurality of cardiopulmonary variables from a training human subject is input to the encoding neural network, a second duration of the training data, substantially nonoverlapping in time with said first duration, comprising a substantially contiguous time series of said selected plurality of cardiopulmonary variables from the training human subject, provides input to the estimation neural network and wherein the estimation neural network provides the estimate of the at least one excluded variable; a functional capacity estimator that is configured to accept as input a cardio profile vector generated by the trained encoding neural network, and to output an estimate of a metric of functional capacity, wherein the control circuit is further configured to train said functional capacity estimator using a plurality of matched examples to produce a trained functional capacity estimator, each of the matched examples comprising a cardio profile vector matched with a corresponding measured functional capacity metric of that person, to enable regression of an input of a cardio profile vector to an estimate of the metric of functional capacity; wherein the trained encoding neural network and the trained functional capacity estimator are deployed to accept as input a duration of monitored data from a monitored human subject, comprising substantially contiguous time series of said selected plurality of cardiopulmonary variables, generate a current cardio profile vector for the monitored human subject, and generate from the current cardio profile vector a current estimate of the metric of functional capacity; and wherein, based upon the current estimate of functional capacity, one or more actions are performed, the one or more actions selected from the group consisting of: the control circuit renders a display on a display screen of the current estimate in a time series with prior estimates to a clinician for review of possible health changes in the monitored human subject; the control circuit compares the current estimate to prior estimates and testing for a change whereupon an electronic alert is triggered and transmitted to a clinician to investigate the health of the monitored human; the control circuit compares the current estimate to prior estimates and testing for a change whereupon the control circuit transmits an electronic questionnaire to the monitored human subject; the control circuit compares the current estimate to prior estimates and testing for a change whereupon the control circuit makes an entry in an electronic medical record of the monitored human subject indicating a change in health of the monitored human subject occurred; the control circuit compares the current estimate to estimates from other monitored human subjects, in order to quantify health affects between at least a control group receiving a first intervention and a test group receiving a second intervention in a clinical trial; and the control circuit transmits an electronic control signal that controls the operation or sets a parameter of a medical device associated with treating or monitoring the monitored human subject.
16. The system of claim 15 , wherein the functional capacity is VO2Max.
17. The system of claim 15 , wherein the time series of selected plurality of cardiopulmonary variables is obtained by sensors that are non-invasively secured to the skin of the humans.
18. The system of claim 15 , wherein the time series of selected plurality of cardiopulmonary variables is obtained by sensors and the sensors are selected from the group consisting of a camera, an electrocardiographic sensor, a light sensor, an accelerometer, an RF energy sensor, a temperature sensor, and a gyroscopic sensor.
19. The system of claim 15 , wherein the functional capacity estimator is implemented by the control circuit and is configured to generate the current estimate of the metric of functional capacity using one of: a linear regression technique, a decision tree, a random forest estimation, or a gradient boosting model.
20. The system of claim 15 , wherein functional capacity estimator comprises an estimation neural network.
21. The system of claim 15 , wherein the cardiopulmonary variables comprise one or more of: a heart rate, a measure of physical activity or motion, a time domain heart rate variability, a respiration rate, a tilt angle, an A-fib probability, and a sample time difference.
22. The system of claim 15 , wherein the current cardio profile vector comprises a plurality of real numbers, each of the real numbers associate with one or more of the cardiopulmonary variables.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
July 18, 2019
March 10, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.